metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_8_task_2_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-2-difficulty-8
results:
- task:
type: sub-task
name: maximize_preparing_non_burning_trees
task-id: 2
difficulty-id: 8
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.17500000521540643 +/- 0.19098850845354493
name: Crash Count
verified: true
- type: extinguishing_trees
value: 5.816666756570339 +/- 11.8174346066285
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 29.08333278298378 +/- 59.08717051646657
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.15000000447034836 +/- 0.24720662360385337
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.975 +/- 0.11180339887498947
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 510.04166743159294 +/- 568.7866281385685
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 2550.2083440065385 +/- 2843.9331445458665
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 38.5666665315628 +/- 20.809101562250987
name: Water Drop
verified: true
- type: water_pickup
value: 38.183333325386045 +/- 20.797681456595466
name: Water Pickup
verified: true
- type: cumulative_reward
value: 2953.239129829407 +/- 2575.5043197313657
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 8 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 8
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment